© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 6-RES-JB
    11. 24454
    Prev
    Next
    INDEX
    Explanations

    instances of phrases with the word "out" being used in a context of expressing a stance or opinion

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to publicly expressing a position or opinion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nesota
    -0.68
    anooga
    -0.64
    Login
    -0.64
    ille
    -0.60
    gee
    -0.58
     rede
    -0.57
     addictive
    -0.57
    cius
    -0.56
     Syd
    -0.56
    olesterol
    -0.55
    POSITIVE LOGITS
    fitted
    0.95
    doors
    0.80
    smart
    0.76
    skirts
    0.75
    wards
    0.75
     swinging
    0.73
    fitting
    0.69
    bright
    0.68
    lier
    0.68
    stretched
    0.68
    Activations Density 0.032%

    No Known Activations